CONTROL OF ADEPT-ONE SCARA ROBOT USING NEURAL NETWORKS

This paper presents an enhanced feedback error learning control (EFELC ) strategy for an n-degree-of-freedom robotic manipulator, It covers t he design and simulation study of the neural-network-based controller for the manipulator with a view of tracking a predetermined trajectory of motion in the joint space, An industrial robotic manipulator, Adep t One Robot, was used to evaluate the effectiveness of the proposed sc heme, The Adept One Robot was simulated as a three-axis manipulator wi th the dynamics of the tool (fourth link) neglected and the mass of th e load incorporated into the mass of the third link, For simplicity, o nly the first two joints of the manipulator were considered in the sim ulation study, The overall performance of the control system under dif ferent conditions, namely, trajectory tracking, variations in trajecto ry, and different initial weight values were studied and comparison ma de with the existing feedback error learning control (FELC) strategy. The enhanced version was shown to outperform the existing method.